Neurobiology of Language and Bilingualism

GPT-2's activations predict the degree of semantic comprehension in the human brain

Across 101 listeners, how well GPT-2 layer-8 activations predict fMRI responses to spoken stories tracks story comprehension, with a correlation of R = 0.50 across subject-story pairs.

Thinking ahead: prediction in context as a keystone of language in humans and machines

In nine epilepsy patients, cortical activity carries next-word information up to 800 ms before onset, tracks GPT-2 surprise after onset, and fits GPT-2 contextual embeddings better than static ones.

Language processing in brains and deep neural networks: computational convergence and its limits

In 3,600 transformer checkpoints compared with fMRI and MEG of 102 readers, middle layers best predict brain activity and grow more brain-like as word-prediction accuracy improves; input embeddings diverge.